Adding a module that mimics part of the brain can prevent common errors made by computer vision models.

What's SSUP? The Sample, Simulate, Update cognitive model developed by MIT researchers learns to use tools like humans do.

Recurrent processing via prefrontal cortex, necessary for quick visual object processing in primates, provides a key insight for developing brain-like artificial intelligence.

In some situations, asking “what if everyone did that?” is a common strategy for judging whether an action is right or wrong.

New statistical model may help scientists understand how animals infer whether surroundings are novel or haven’t changed enough to be a new context.

Part of the visual cortex dedicated to recognizing objects appears predisposed to identifying words and letters, a study finds.

Recent advances give theoretical insight into why deep learning networks are successful.

Acoustic and biological constraints shape how we hear harmony across cultures.

Computer model of face processing could reveal how the brain produces richly detailed visual representations so quickly.

Researchers discover that no magic is required to explain why deep networks generalize despite going against statistical intuition.